© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    phrases indicating increased difficulty or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate increasing difficulty or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EVA
    -0.74
    ivo
    -0.71
    inate
    -0.70
    Kings
    -0.69
    reen
    -0.69
    abet
    -0.68
    Saint
    -0.67
     Charity
    -0.67
    Liber
    -0.66
     Gazette
    -0.64
    POSITIVE LOGITS
     than
    1.22
     Than
    1.01
     harder
    0.85
     behaved
    0.82
     compr
    0.76
     forgiving
    0.76
     resil
    0.74
    nces
    0.74
     "$:/
    0.74
    ModLoader
    0.73
    Activations Density 0.012%

    No Known Activations